© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72145
    Prev
    Next
    INDEX
    Explanations

    opinion favourite new implementing collect survey select this year

    np_acts-logits-general · gemini-2.5-flash-lite

    personalities and qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    امات
    0.47
    鸣
    0.47
    应用程序
    0.46
    صاص
    0.45
     preguntar
    0.45
     deliver
    0.45
    两
    0.45
    但是
    0.44
    这是一个
    0.44
    权限
    0.43
    POSITIVE LOGITS
    bien
    0.45
    加えて
    0.44
     архівної
    0.44
    unchecked
    0.42
    gist
    0.42
    retirement
    0.42
    OLYBD
    0.42
     एकदम
    0.41
     প্রথমেই
    0.41
    cris
    0.40
    Activations Density 0.002%

    No Known Activations